Raw neurons in protein language models are polysemantic: a single dimension responds to hydrophobicity, secondary structure, and family artifacts at once. Sparse autoencoders (SAEs) promise monosemantic features — but the promise needs auditing.
Why SAEs over raw dimensions
- Superposition: PLMs pack more concepts than dimensions. SAEs expand the basis.
- Comparability: features are easier to align across layers and checkpoints.
- Probe targets: a sparse feature is a cleaner unit for recoverability tests.
A minimal training sketch
loss = mse(x, decode(features)) + l1 * features.abs().mean()The real work is not the loss — it is the evaluation of what the features mean.
What SAEs cannot tell you
- Whether a feature is used downstream, or merely present.
- Whether feature–label correlation survives family-held-out splits.
- Whether the dictionary is stable across seeds.
Each of these needs its own experiment. Interpretability findings without structured evaluation are hypotheses, not conclusions.
蛋白质语言模型中的单个神经元通常具有多义性：同一维度可能同时响应疏水性、二级结构和蛋白质家族特征。稀疏自编码器（SAE）希望得到含义更单一的特征，但这种含义仍然需要严格检验。
为什么不用原始维度，而使用 SAE
- 叠加表示：PLM 需要在有限维度中容纳更多概念，SAE 可以扩展表示基。
- 便于比较：特征更容易在不同层和不同检查点之间对齐。
- 适合作为探针目标：稀疏特征通常比原始维度更适合做可恢复性测试。
最小训练示例
loss = mse(x, decode(features)) + l1 * features.abs().mean()真正困难的部分不在损失函数，而在于如何评估这些特征到底表示什么。
SAE 无法直接告诉我们什么
- 一个特征是否真正被下游任务使用，还是只是存在于表征中。
- 特征与标签之间的相关性，能否通过家族留出评估。
- 学到的特征字典在不同随机种子下是否稳定。
这些问题需要各自独立的实验。没有结构化评估的可解释性结果，只能作为假设，不能直接当作结论。